© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211505
    Prev
    Next
    INDEX
    Explanations

    capacity offers a

    np_acts-logits-general · gemini-2.5-flash-lite

    spatial coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Include
    0.46
       
    0.43
    測
    0.42
     care
    0.42
    idE
    0.41
    Name
    0.41
    Pour
    0.40
    🧬
    0.39
     prefs
    0.39
    WHERE
    0.39
    POSITIVE LOGITS
    几次
    0.52
     кілька
    0.50
     MSNBC
    0.48
     Warren
    0.46
     ক্রমাগত
    0.46
     компьютера
    0.46
     аўтаматы
    0.46
     момент
    0.45
     چندین
    0.45
     вскоре
    0.45
    Activations Density 0.000%

    No Known Activations